© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38365
    Prev
    Next
    INDEX
    Explanations

    EC numbers and classifications

    np_acts-logits-general · gemini-2.5-flash-lite

    numeric identifiers like dates, version numbers, EC numbers, or publication reference numbers.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     not
    -1.95
     something
    -1.86
     will
    -1.80
     it
    -1.55
     know
    -1.52
     etc
    -1.51
     два
    -1.50
    </h2>
    -1.45
     не
    -1.44
     different
    -1.41
    POSITIVE LOGITS
    是一款
    1.46
     lada
    1.39
    !!:
    1.32
    ฅ
    1.30
    ungsver
    1.30
     pâte
    1.27
    くて
    1.25
     lunettes
    1.25
     辣
    1.23
     louer
    1.23
    Activations Density 0.217%

    No Known Activations